Spend in this session

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the bar is lower. The description still adds real context: the measurement window is since server start, the breakdown is per tool, the values relate to two named guard variables, and 'Local, free' tells the agent the call costs nothing and makes no network request.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, zero filler, with the core scope (session spend, per tool) front-loaded before the guard context. The clipped 'Local, free.' fragment still earns its place by conveying cost and network behavior.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a parameterless, read-only, locally computed status tool, the description covers scope, grouping, and the limits being compared against. It does not sketch the response shape (a per-tool map of dollar amounts), but with no output schema and a trivial input, that is a minor omission.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes zero parameters, which is the baseline-4 case; there is nothing for the description to disambiguate. The schema is empty and 100% covered, so no compensation is needed.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific resource and scope: spend accrued by this MCP server since it started, broken down per tool. It does not explicitly distinguish itself from near-siblings such as carpe_balance, carpe_usage_summary, or carpe_key_usage, so an agent must infer the difference from the word 'session'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: 'Local, free' signals this is a cheap call to check spend against the CARPE_MAX_SPEND_USD and CARPE_MAX_PER_CALL_USD guards, which hints at budget-checking use. There is no explicit when-to-use/when-not-to-use statement and no routing to alternative spend or usage tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.